frontend-design-pro
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied UI component names and code snippets to perform audits and polishes, creating a potential surface for indirect prompt injection.\n- Ingestion points: The [组件名] (component name) parameter used in commands such as /audit, /critique, and /polish in SKILL.md.\n- Boundary markers: Absent; the skill does not use specific delimiters or instructions to isolate user-provided code from the system logic.\n- Capability inventory: The skill is focused on design critique and frontend code generation; no dangerous operations like shell access, network exfiltration, or file system modifications were found.\n- Sanitization: Absent.\n- [EXTERNAL_DOWNLOADS]: The skill documentation refers to the impeccable design project on GitHub for its core principles.\n- Source: https://github.com/pbakaus/impeccable
Audit Metadata